—————— ConvNeXt ——————--


Facebook propose ConvNeXt, a pure ConvNet model constructed entirely from standard ConvNet modules. ConvNeXt is accurate, efficient, scalable and very simple in design.

Github: https://github.com/facebookresearch/ConvNeXt

Paper: https://arxiv.org/abs/2201.03545

invite your friends 🌹🌹
@deeplearning_ai

5TH UG2+ PRIZE CHALLENGE CVPR 2022
$10K PRIZES

https://cvpr2022.ug2challenge.org/

https://docs.google.com/forms/d/e/1FAIpQLSeK0j4cPRNFQbm27qMfaTr27wRQ6tXMV2gmohjaJlbn2fAX0A/viewform

https://cmt3.research.microsoft.com/User/Login?ReturnUrl=%2FUG2CHALLENGE2022


invite your friends 🌹🌹
@deeplearning_ai

The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

https://www.ritchieng.com/the-incredible-pytorch/

https://github.com/ritchieng/the-incredible-pytorch

@deeplearning_ai

321 Open Source Pytorch Implementation Software Projects
Free and open source pytorch implementation code projects including engines, APIs, generators, and tools.

https://opensourcelibs.com/libs/pytorch-implementation

invite your friends 🌹🌹
t.iss.one/MachineLearning_Programming

.

Want to jump ahead in artificial intelligence and/or digital pathology? Excited to share that after 2+ years of development PathML 2.0 is out! An open source #computational #pathology software library created by Dana-Farber Cancer Institute/Harvard Medical School and Weill Cornell Medicine led by Massimo Loda to lower the barrier to entry to #digitalpathology and #artificialintelligence , and streamline all #imageanalysis or #deeplearning workflows.

⭐ Code: https://github.com/Dana-Farber-AIOS/pathml

Image Super Resolution - PyImageSearch

https://pyimagesearch.com/2022/02/14/image-super-resolution/

invite your friends 🌹🌹
@Deeplearning_ai

.

Multi Task Learning for 3D segmentation

Perception stack of an Autonomous Driving system often contains multiple neural networks working together to predict bounding boxes, segmentation maps, depth maps, lane lines etc. Having a separate neural network for each task creates an heavy impact on system's processing speed.

https://github.com/adithyagaurav/Multi_Task_Learning


invite your friends 🌹🌹
@Deeplearning_ai

Realtime Object-aware Monocular Depth Estimation in Onboard Systems

Video Paper Bibtex

invite your friends 🌹🌹
@Deeplearning_ai

FLAG: Flow-based 3D Avatar Generation
from Sparse Observations.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅FLow-based Avatar Generative
✅Conditional distro of body pose
✅Exact pose likelihood process
✅Invertibility -> oracle latent code

[PAPER] [Project Page]


invite your friends 🌹🌹
@Deeplearning_ai

If you are learning Machine Learning and wants to make end-to-end Machine Learning real-world projects, then this website can be a great resource for you.

It has project bundle(Dragon bundle) comprising more than 550+ real-world projects in ML, DL, DS, CV and NLP and PYTHON3.

More details are showned in the image above.

- Each project comes with required Dataset, complete source code(Python3) and documentation along with explanatory comments so that even beginner can understand.

- Life time access and projects are getting updates each month.

You can download the list of complete 550+ projects from our website.

Visit our website for more information.
Website Link:
https://tensorprojects.com/dragonbundle

At DAIR.AI we heart open education. We are excited to share some of the best and most recent machine learning courses available on YouTube.

Hot topics:
1. Stanford CS229: Machine Learning
2. Practical Deep Learning for Coders (2020)
3. Deep Unsupervised Learning
4. Advanced NLP
5. Deep Learning for Computer Vision
6. Deep Reinforcement Learning
7. Full Stack Deep Learning
8. Self-Driving Cars (Tübingen)

https://github.com/dair-ai/ML-YouTube-Courses

invite your friends 🌹🌹
@Deeplearning_ai

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

https://github.com/Garfield-kh/PoseTriplet



invite your friends 🌹🌹
@Deeplearning_ai

Accelerate AI training in a few lines of code without changing the training setup.


https://github.com/nebuly-ai/nebulgym



invite your friends 🌹🌹
@Deeplearning_ai

Kickstart your developer journey with free courses and cash rewards for you time in one place 📚💰

Use code "aideeplearning" to gain access: https://bit.ly/3KU21bq 👈

StackUp is a platform for devs where you can learn programming & Web3.0 technologies, all while earning. Get rewarded for completing a variety of learning quests.

With new campaigns each week, you can earn from a pool of over 10 000USD in cash rewards each month. This month's campaign has a total pool of 30 000USD worth of rewards! 🚀

EG3D: Efficient Geometry-aware 3D Generative Adversarial Networks

Official PyTorch implementation of the CVPR 2022 paper.

Project page: https://nvlabs.github.io/eg3d/

Paper: https://arxiv.org/abs/2112.07945

Source code: https://github.com/NVlabs/eg3d


invite your friends 🌹🌹
@Deeplearning_ai

CVPR 2022 Open Access...


Open Access versions, provided by the Computer Vision Foundation.
Except for the watermark, they are identical to the accepted versions; the final published version of the proceedings is available on IEEE Xplore.

https://openaccess.thecvf.com/CVPR2022?day=2022-06-21



invite your friends 🌹🌹
@Deeplearning_ai